Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 8322
    Prev
    Next
    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash

    This neuron detects MSBuild XML “Import” statements (i.e. the `<Import Project="…\.props" />` lines).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ffen
    -0.08
    적으로
    -0.07
     builds
    -0.07
     katı
    -0.06
    dur
    -0.06
    APPLE
    -0.06
    ao
    -0.06
    acher
    -0.06
    _sol
    -0.06
    azione
    -0.06
    POSITIVE LOGITS
    Speed
    0.06
    JsonObject
    0.06
    _putstr
    0.06
    .enum
    0.06
    -react
    0.06
    ('/')[-
    0.06
    μένοι
    0.06
     Consumer
    0.06
     Pee
    0.05
     Throw
    0.05
    Activations Density 0.001%

    No Known Activations